Journal article Closed Access

Finding parallel functional pearls: Automatic parallel recursion scheme detection in Haskell functions via anti-unification

Barwell, Adam David; Christopher, Brown; Hammond, Kevin

This paper describes a new technique for identifying potentially parallelisable code structures in functional programs. Higher-order functions enable simple and easily understood abstractions that can be used to implement a variety of common recursion schemes, such as maps and folds over traversable data structures. Many of these recursion schemes have natural parallel implementations in the form of algorithmic skeletons. This paper presents a technique that detects instances of potentially parallelisable recursion schemes in Haskell 98 functions. Unusually, we exploit anti-unification to expose these recursion schemes from source-level definitions whose structures match a recursion scheme, but which are not necessarily written directly in terms of mapsfolds, etc. This allows us to automatically introduce parallelism, without requiring the programmer to structure their code a priori in terms of specific higher-order functions. We have implemented our approach in the Haskell refactoring tool, HaRe, and demonstrated its use on a range of common benchmarking examples. Using our technique, we show that recursion schemes can be easily detected, that parallel implementations can be easily introduced, and that we can achieve real parallel speedups (up to 23.79x the sequential performance on 28 physical cores, or 32.93x the sequential performance with hyper-threading enabled).

 

This work has been partially supported by the EU H2020 grant ''RePhrase: Refactoring Parallel Heterogeneous Resource-Aware Applications–a Software Engineering Approach'' (ICT-644235), by COST Action IC1202 (TACLe), supported by COST (European Co- operation in Science and Technology) by EPSRC grant ''Discovery: Pattern Discovery and Program Shaping for Manycore Systems'' (EP/P020631/1), and by Scottish Enterprise PS7305CA44.
Closed Access

Files are not publicly accessible.

9
0
views
downloads
Views 9
Downloads 0
Data volume 0 Bytes
Unique views 9
Unique downloads 0

Share

Cite as